添加新卡片到指定卡组
AI agents use anki_add_note to create or update resources in TalkToAnki — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TalkToAnki environment.
This tool creates new flashcard notes in a user's Anki deck. Creation of data without irreversible deletion or external financial/code execution impacts classifies as Write. Severity is medium because misuse could pollute a user's study decks with incorrect or spam content, but the damage is reversible via the anki_delete_notes tool present on the same server.
From the tool's definition Tool name 'anki_add_note' and description '添加新卡片到指定卡组' (Add new flashcard to specified deck) indicate creation of new data in Anki flashcard system.
Attacks that exploit this kind of access
添加新卡片到指定卡组. It is categorised as a Write tool in the TalkToAnki MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the TalkToAnki MCP server in PolicyLayer and add a rule for anki_add_note: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches TalkToAnki. Nothing to install.
anki_add_note is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the anki_add_note rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for anki_add_note. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
anki_add_note is provided by the TalkToAnki MCP server (muxuuu/talktoanki). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →